{
  "best_metric": 1.7675107717514038,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.4672897196261682,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.2050091177225113,
      "learning_rate": 5e-05,
      "loss": 1.96,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "eval_loss": 2.763558864593506,
      "eval_runtime": 16.1331,
      "eval_samples_per_second": 44.691,
      "eval_steps_per_second": 5.641,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.32572096586227417,
      "learning_rate": 0.0001,
      "loss": 1.9598,
      "step": 2
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 0.4188697338104248,
      "learning_rate": 9.989294616193017e-05,
      "loss": 2.1013,
      "step": 3
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 0.5268757343292236,
      "learning_rate": 9.957224306869053e-05,
      "loss": 2.1676,
      "step": 4
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 0.9174801707267761,
      "learning_rate": 9.903926402016153e-05,
      "loss": 2.2121,
      "step": 5
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.9002692699432373,
      "learning_rate": 9.829629131445342e-05,
      "loss": 2.2158,
      "step": 6
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 0.7341592907905579,
      "learning_rate": 9.73465064747553e-05,
      "loss": 2.2262,
      "step": 7
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 0.9379644989967346,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2747,
      "step": 8
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 1.350318193435669,
      "learning_rate": 9.484363707663442e-05,
      "loss": 2.0752,
      "step": 9
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.811265468597412,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1028,
      "step": 10
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 3.3716864585876465,
      "learning_rate": 9.157348061512727e-05,
      "loss": 2.2434,
      "step": 11
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 5.006383419036865,
      "learning_rate": 8.966766701456177e-05,
      "loss": 2.4931,
      "step": 12
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 1.7680565118789673,
      "learning_rate": 8.759199037394887e-05,
      "loss": 1.6765,
      "step": 13
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 2.226541519165039,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9434,
      "step": 14
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 2.2633767127990723,
      "learning_rate": 8.296729075500344e-05,
      "loss": 2.0103,
      "step": 15
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.7551491260528564,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.9887,
      "step": 16
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 1.1776738166809082,
      "learning_rate": 7.777851165098012e-05,
      "loss": 1.9628,
      "step": 17
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.48549848794937134,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.0331,
      "step": 18
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 1.4241870641708374,
      "learning_rate": 7.211443451095007e-05,
      "loss": 2.0393,
      "step": 19
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.8703410625457764,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.9913,
      "step": 20
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 2.2542777061462402,
      "learning_rate": 6.607197326515808e-05,
      "loss": 1.7357,
      "step": 21
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 2.6950325965881348,
      "learning_rate": 6.294095225512603e-05,
      "loss": 1.8501,
      "step": 22
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 3.4160990715026855,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 1.9373,
      "step": 23
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 4.2858991622924805,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 1.7563,
      "step": 24
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 12.01784896850586,
      "learning_rate": 5.327015646150716e-05,
      "loss": 2.602,
      "step": 25
    },
    {
      "epoch": 0.2336448598130841,
      "eval_loss": 1.826279878616333,
      "eval_runtime": 16.1695,
      "eval_samples_per_second": 44.59,
      "eval_steps_per_second": 5.628,
      "step": 25
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 0.31022751331329346,
      "learning_rate": 5e-05,
      "loss": 1.572,
      "step": 26
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.5702259540557861,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 1.877,
      "step": 27
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.7507174015045166,
      "learning_rate": 4.347369038899744e-05,
      "loss": 1.7807,
      "step": 28
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.7919750809669495,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 1.944,
      "step": 29
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.8161137700080872,
      "learning_rate": 3.705904774487396e-05,
      "loss": 1.8851,
      "step": 30
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.5553084015846252,
      "learning_rate": 3.392802673484193e-05,
      "loss": 2.0236,
      "step": 31
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.49405890703201294,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9551,
      "step": 32
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.4366614818572998,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 1.8344,
      "step": 33
    },
    {
      "epoch": 0.3177570093457944,
      "grad_norm": 0.46041783690452576,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.7414,
      "step": 34
    },
    {
      "epoch": 0.32710280373831774,
      "grad_norm": 0.7788172364234924,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 1.7514,
      "step": 35
    },
    {
      "epoch": 0.3364485981308411,
      "grad_norm": 1.5431926250457764,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 1.722,
      "step": 36
    },
    {
      "epoch": 0.34579439252336447,
      "grad_norm": 2.5300698280334473,
      "learning_rate": 1.703270924499656e-05,
      "loss": 1.6433,
      "step": 37
    },
    {
      "epoch": 0.35514018691588783,
      "grad_norm": 0.3177616000175476,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.6753,
      "step": 38
    },
    {
      "epoch": 0.3644859813084112,
      "grad_norm": 0.23859432339668274,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 1.6159,
      "step": 39
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.2884484827518463,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 1.8563,
      "step": 40
    },
    {
      "epoch": 0.38317757009345793,
      "grad_norm": 0.3251397907733917,
      "learning_rate": 8.426519384872733e-06,
      "loss": 1.8588,
      "step": 41
    },
    {
      "epoch": 0.3925233644859813,
      "grad_norm": 0.30368906259536743,
      "learning_rate": 6.698729810778065e-06,
      "loss": 1.8786,
      "step": 42
    },
    {
      "epoch": 0.40186915887850466,
      "grad_norm": 0.3018438220024109,
      "learning_rate": 5.156362923365588e-06,
      "loss": 1.9238,
      "step": 43
    },
    {
      "epoch": 0.411214953271028,
      "grad_norm": 0.2993268072605133,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9523,
      "step": 44
    },
    {
      "epoch": 0.4205607476635514,
      "grad_norm": 0.37869080901145935,
      "learning_rate": 2.653493525244721e-06,
      "loss": 1.9622,
      "step": 45
    },
    {
      "epoch": 0.42990654205607476,
      "grad_norm": 0.4851050078868866,
      "learning_rate": 1.70370868554659e-06,
      "loss": 1.853,
      "step": 46
    },
    {
      "epoch": 0.4392523364485981,
      "grad_norm": 0.6026566624641418,
      "learning_rate": 9.607359798384785e-07,
      "loss": 1.6661,
      "step": 47
    },
    {
      "epoch": 0.4485981308411215,
      "grad_norm": 1.0885943174362183,
      "learning_rate": 4.277569313094809e-07,
      "loss": 1.9348,
      "step": 48
    },
    {
      "epoch": 0.45794392523364486,
      "grad_norm": 1.734622836112976,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 1.757,
      "step": 49
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 5.6349005699157715,
      "learning_rate": 0.0,
      "loss": 2.5496,
      "step": 50
    },
    {
      "epoch": 0.4672897196261682,
      "eval_loss": 1.7675107717514038,
      "eval_runtime": 15.5593,
      "eval_samples_per_second": 46.339,
      "eval_steps_per_second": 5.849,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0635096147099648e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}